© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139864
    Prev
    Next
    INDEX
    Explanations

    cerebral palsy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poteva
    0.63
     ଶ
    0.61
     myeloma
    0.60
     тю
    0.59
     mandala
    0.57
     judicial
    0.57
     possibile
    0.56
     maggio
    0.56
     మధ్య
    0.56
     машинасы
    0.56
    POSITIVE LOGITS
    イッチ
    0.52
    Ll
    0.51
    {
    0.50
    Graz
    0.50
    €
    0.47
    私たち
    0.44
     Graz
    0.44
    graz
    0.44
    which
    0.43
    とても
    0.43
    Activations Density 0.001%

    No Known Activations